A Model for Recommending Related Research Papers: A Natural Language Processing Approach
- Authors: Van Heerden, Juandre Anton
- Date: 2022-04
- Subjects: Electronic information resources , Research
- Language: English
- Type: Master's theses , text
- Identifier: http://hdl.handle.net/10948/58495 , vital:59651
- Description: The volume of information generated lately has led to information overload, which has impacted researchers’ decision-making capabilities. Researchers have access to a variety of digital libraries to retrieve information. Digital libraries often offer access to a number of journal articles and books. Although digital libraries have search mechanisms it still takes much time to find related research papers. The main aim of this study was to develop a model that uses machine learning techniques to recommend related research papers. The conceptual model was informed by literature on recommender systems in other domains. Furthermore, a literature survey on machine learning techniques helped to identify candidate techniques that could be used. The model comprises four phases. These phases are completed twice, the first time for learning from the data and the second time when a recommendation is sought. The four phases are: (1) identify and remove stopwords, (2) stemming the data, (3) identify the topics for the model, and (4) measuring similarity between documents. The model is implemented and demonstrated using a prototype to recommend research papers using a natural language processing approach. The prototype underwent three iterations. The first iteration focused on understanding the problem domain by exploring how recommender systems and related techniques work. The second iteration focused on pre-processing techniques, topic modeling and similarity measures of two probability distributions. The third iteration focused on refining the prototype, and documenting the lessons learned throughout the process. Practical lessons were learned while finalising the model and constructing the prototype. These practical lessons should help to identify opportunities for future research. , Thesis (MA) -- Faculty of Engineering, the Built Environment, and Technology, 2022
- Full Text:
- Date Issued: 2022-04
A case study of the research careers of women academics: constraints and enablements
- Authors: Obers, Nöelle Marie Thérèse
- Date: 2013
- Subjects: Career success , Research , Women college teachers , Women in higher education , Sex discrimination in higher education
- Language: English
- Type: Thesis , Masters , MEd
- Identifier: vital:1313 , http://hdl.handle.net/10962/d1001575
- Description: The purpose of this research is to investigate constraints that women academics experience in their research careers and how enablements, particularly in the form of mentoring relationships and support structures, can impact on their research career development in the context of the new knowledge economy of Higher Education. The research was a case study of one South African Institution and used a mixed method approach. Social realism underpinned the research. Data was collected and analysed within the spheres of structure, culture and agency, using critical discourse analysis, interpretation and abstraction strategies. I investigated how women researchers understand and experience career success and what they perceive and experience as enablements and constraints to their research careers. Institutional support structures and cultures were examined with a focus on the role of the Head of Department. I explored mentoring and questioned whether the agency of women academics is empowered by mentoring and supportive structures to overcome constraints to their research productivity and the development of their careers. Gender-based issues of inequity, low self-esteem and accrual of social capital appear to be the underlying factors affecting how women perform in the research arena and advance within the institution. It was found that mentoring is a generative mechanism that has a favourable impact on women academics as it enables them to overcome obstacles to research productivity and career advancement.
- Full Text:
- Date Issued: 2013